Graph neural networks are intimately related to partial differential equations governing information diffusion on graphs. Thinking of GNNs as PDEs leads to a new broad class of graph ML methods.
H. Nguyen, N. Nguyen, H. Doan, Z. Ahmadi, T. Doan, и L. Jiang. Proceedings of the ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, New York, NY, USA, Association for Computing Machinery, (ноября 2022)